Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 306 334 945 657 633 636 325 450 251 283 241  47 596 727 878 743 452 348 239 498
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 241 325  47 450 306  NA 251 334  NA 452 283 636 348 878 657 945 596  NA 498 239 633 727 743
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 2 1 5 4 3 3 3 4 1 1
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "w" "t" "g" "l" "i" "L" "K" "O" "J" "I"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 3
which( manyNumbersWithNA > 900 )
[1] 16
which( is.na( manyNumbersWithNA ) )
[1]  6  9 18

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 945
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 945
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 945

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "L" "K" "O" "J" "I"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "w" "t" "g" "l" "i"
manyNumbers %in% 300:600
 [1]  TRUE  TRUE FALSE FALSE FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE  TRUE  TRUE FALSE  TRUE
which( manyNumbers %in% 300:600 )
[1]  1  2  7  8 13 17 18 20
sum( manyNumbers %in% 300:600 )
[1] 8

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "small" "small" "small" "small" NA      "small" "small" NA      "small" "small" "large" "small" "large" "large" "large" "large" NA      "small" "small" "large"
[22] "large" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "small"   "small"   "small"   "small"   "UNKNOWN" "small"   "small"   "UNKNOWN" "small"   "small"   "large"   "small"   "large"   "large"   "large"   "large"  
[18] "UNKNOWN" "small"   "small"   "large"   "large"   "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0   0   0   0   0  NA   0   0  NA   0   0 636   0 878 657 945 596  NA   0   0 633 727 743

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 2 1 5 4 3
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  2  1  5  4  3
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 16
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 945
which.min( manyNumbersWithNA )
[1] 3
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 47
range( manyNumbersWithNA, na.rm = TRUE )
[1]  47 945

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 241 325  47 450 306  NA 251 334  NA 452 283 636 348 878 657 945 596  NA 498 239 633 727 743
sort( manyNumbersWithNA )
 [1]  47 239 241 251 283 306 325 334 348 450 452 498 596 633 636 657 727 743 878 945
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  47 239 241 251 283 306 325 334 348 450 452 498 596 633 636 657 727 743 878 945  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 945 878 743 727 657 636 633 596 498 452 450 348 334 325 306 283 251 241 239  47  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 241 325  47 450 306
order( manyNumbersWithNA[1:5] )
[1] 3 1 5 2 4
rank( manyNumbersWithNA[1:5] )
[1] 2 4 1 5 3
sort( mixedLetters )
 [1] "g" "i" "I" "J" "K" "l" "L" "O" "t" "w"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1]  6.5  1.5  4.0  6.5 10.0  4.0  8.5  1.5  8.5  4.0
rank( manyDuplicates, ties.method = "min" )
 [1]  6  1  3  6 10  3  8  1  8  3
rank( manyDuplicates, ties.method = "random" )
 [1]  6  2  5  7 10  3  9  1  8  4

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000  0.2212481 -0.4826574 -2.4718006 -0.9079842 -1.3694906  0.6877984  1.0930027 -0.1856917 -0.1215355  0.4844100
round( v, 0 )
 [1] -1  0  0  0  1  0  0 -2 -1 -1  1  1  0  0  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  0.2 -0.5 -2.5 -0.9 -1.4  0.7  1.1 -0.2 -0.1  0.5
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.22 -0.48 -2.47 -0.91 -1.37  0.69  1.09 -0.19 -0.12  0.48
floor( v )
 [1] -1 -1  0  0  1  0 -1 -3 -1 -2  0  1 -1 -1  0
ceiling( v )
 [1] -1  0  0  1  1  1  0 -2  0 -1  1  2  0  0  1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2023 Biomedical Data Sciences (BDS) | LUMC